Position Paper: Bridging the Gap Between Machine Learning and Sensitivity Analysis

TL;DR

This paper advocates for viewing machine learning model explanations through the lens of sensitivity analysis, proposing a unified framework that connects ML interpretability with established SA methodologies across various fields.

Contribution

It formally demonstrates how ML processes can be understood as systems suitable for sensitivity analysis and relates existing interpretation methods to this perspective.

Findings

ML interpretation methods can be framed as sensitivity analysis techniques

A unified view enhances understanding of ML explanations across disciplines

Potential for applying diverse SA techniques to improve ML interpretability

Abstract

We argue that interpretations of machine learning (ML) models or the model-building process can be seen as a form of sensitivity analysis (SA), a general methodology used to explain complex systems in many fields such as environmental modeling, engineering, or economics. We address both researchers and practitioners, calling attention to the benefits of a unified SA-based view of explanations in ML and the necessity to fully credit related work. We bridge the gap between both fields by formally describing how (a) the ML process is a system suitable for SA, (b) how existing ML interpretation methods relate to this perspective, and (c) how other SA techniques could be applied to ML.